Supercharge Your Innovation With Domain-Expert AI Agents!

Flame recognition method based on infrared multi-feature joint technology

A combined technology and flame recognition technology, which is applied in the field of flame recognition based on infrared multi-feature combined technology, can solve problems such as difficulty in removing flame background, difficulty in using flame texture information with excessively high temperature or brighter temperature, and inability to use flame temperature information. , to achieve the effect of accurately identifying the flame

Active Publication Date: 2021-05-04
SHENYANG HONGJI ELECTRICAL
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In view of this, the purpose of the present invention is to provide a flame recognition method based on infrared multi-feature joint technology, to solve the problem that the temperature information of the flame cannot be used in the prior art, it is difficult to use the texture information of the flame with too high temperature or brighter, it is difficult to Eliminate problems such as flame backgrounds whose shape is similar to flames

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Flame recognition method based on infrared multi-feature joint technology
  • Flame recognition method based on infrared multi-feature joint technology
  • Flame recognition method based on infrared multi-feature joint technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further explained below in conjunction with specific embodiments, but the present invention is not limited thereto.

[0032] The invention provides a flame identification method based on infrared multi-feature joint technology, comprising the following steps:

[0033] S1: Use the infrared camera to obtain the infrared image and temperature information of the monitoring area;

[0034] S2: Find the suspected flame area S, and according to the lowest temperature T of the suspected flame area S min Perform high-pass filtering on the infrared image to filter out the low-temperature background, and further obtain the suspected flame area S 0 , where the suspected flame area S in the infrared image has a temperature greater than the temperature threshold T 0 Or the temperature increases to the temperature sudden change coefficient K 0 Times and K 0 A collection of pixel points more than twice;

[0035] where the temperature threshold T 0 and...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a flame recognition method based on an infrared multi-feature combination technology. Through an infrared thermal imager, objects within the field of view can be monitored all-weather, avoiding the influence of insufficient illumination and interference objects, and using the temperature threshold and The temperature sudden change coefficient can find the suspected flame area, and extract the temperature characteristics of the flame, the motion characteristics of the flame, the contour characteristics and the texture characteristics, and then input the above characteristics into the trained BP neural network to realize the indoor space. Multi-feature joint flame recognition. This method can monitor whether a flame is generated through infrared monitoring, and analyze the collective characteristics and temperature information of the flame more intuitively. At the same time, the method of neural network is used to combine the recognition of multiple characteristics, which improves the stability and recognition rate of the system.

Description

technical field [0001] The invention relates to the field of flame recognition, and in particular provides a flame recognition method based on infrared multi-feature combination technology. Background technique [0002] With the sustained and rapid development of China's economy, fires have an increasing impact on people's lives and property safety, and the requirements for flame identification are also getting higher and higher. Most of the existing technologies use high-definition cameras to monitor flames, and achieve the purpose of flame identification by identifying flame characteristics. While losing temperature information, there will also be interference from backgrounds and other objects. [0003] Existing methods have at least the following disadvantages: [0004] 1. Using a visible light camera, although high-definition flame images can be captured, the most important temperature information for the flame cannot be collected; [0005] 2. The recognition of the f...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06T7/187G06T7/13G06T7/66G06N3/04
Inventor 马胤刚王明威蒋辉张冠男杨娟
Owner SHENYANG HONGJI ELECTRICAL
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More